Fixes & Improvements #316
Fixes & Improvements #316
Conversation
- Fix issue with lunch flow accounts that were imported - Remove the period comparison section from reports
WalkthroughRemoves the period comparison report UI and its server-side builder, migrates Settings dynamic storage from a single hash to per-key entries, restricts Lunchflow importer to linked accounts, adds recurring_transactions metadata columns, and applies small template and initializer safeguards. Changes
Sequence Diagram(s)sequenceDiagram
participant Client
participant ProvidersController as ProvidersController
participant SettingModel as Setting
participant DB as Database
rect rgb(240,248,255)
Note over Client,ProvidersController: Old (batch update)
Client->>ProvidersController: PATCH provider params (dynamic fields)
ProvidersController->>SettingModel: read Setting.var == "dynamic_fields"
SettingModel->>DB: SELECT dynamic_fields row
ProvidersController->>SettingModel: write merged dynamic_fields hash
SettingModel->>DB: UPDATE dynamic_fields row
end
rect rgb(245,245,255)
Note over Client,ProvidersController: New (per-key writes)
Client->>ProvidersController: PATCH provider params (dynamic fields)
ProvidersController->>SettingModel: for each key -> Setting[key] = value
loop per key
SettingModel->>DB: INSERT/UPDATE var = "dynamic:<key>"
end
Note over SettingModel,DB: nil -> delete corresponding row
end
Estimated code review effort🎯 4 (Complex) | ⏱️ ~60 minutes
Possibly related PRs
Suggested labels
Suggested reviewers
Poem
Pre-merge checks and finishing touches❌ Failed checks (1 warning, 1 inconclusive)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
app/models/setting.rb (1)
65-83: Race condition:find_or_initialize_by+save!is not atomic.The comment on line 77 claims to use upsert, but the implementation uses
find_or_initialize_byfollowed bysave!, which is not atomic. Two concurrent processes can both find no record, initialize separate instances, and then encounter a collision on save.This contradicts the PR's objective to prevent atomic update issues and collisions.
Apply this diff to use Rails' atomic upsert:
else # Store as individual dynamic entry dynamic_key = dynamic_key_name(key_str) if value.nil? where(var: dynamic_key).destroy_all else - # Use upsert to avoid conflicts - record = find_or_initialize_by(var: dynamic_key) - record.value = value - record.save! + # Use upsert for atomic operation to avoid race conditions + upsert({ var: dynamic_key, value: value }, unique_by: :var) end endNote: Ensure the database has a unique index on the
varcolumn forupsertto work correctly.
🧹 Nitpick comments (1)
db/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rb (1)
6-17: Migration logic is correct and well-logged.The migration properly identifies and removes orphaned accounts. The logging provides good visibility into the operation.
Consider using
delete_allinstead ofdestroy_allfor better performance since these are orphaned records where callbacks are unlikely to be necessary:- orphaned_accounts.destroy_all + orphaned_accounts.delete_allHowever, if callbacks are needed for proper cleanup (e.g., removing associated records),
destroy_allis the correct choice.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (15)
app/controllers/reports_controller.rb(0 hunks)app/controllers/settings/providers_controller.rb(1 hunks)app/models/lunchflow_item/importer.rb(1 hunks)app/models/provider/configurable.rb(2 hunks)app/models/setting.rb(3 hunks)app/views/reports/_comparison_chart.html.erb(0 hunks)app/views/reports/index.html.erb(0 hunks)config/locales/views/reports/en.yml(0 hunks)db/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rb(1 hunks)db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb(1 hunks)db/schema.rb(2 hunks)test/controllers/reports_controller_test.rb(0 hunks)test/controllers/settings/providers_controller_test.rb(5 hunks)test/models/period_test.rb(0 hunks)test/models/setting_test.rb(2 hunks)
💤 Files with no reviewable changes (6)
- config/locales/views/reports/en.yml
- test/models/period_test.rb
- test/controllers/reports_controller_test.rb
- app/controllers/reports_controller.rb
- app/views/reports/index.html.erb
- app/views/reports/_comparison_chart.html.erb
🧰 Additional context used
📓 Path-based instructions (11)
db/migrate/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Place database migrations under db/migrate/
Simple validations like null checks and unique constraints should be handled by database constraints in migration files.
Files:
db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rbdb/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rb
**/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Ruby style: 2-space indentation; snake_case for methods/variables; CamelCase for classes/modules
Files:
db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rbapp/models/provider/configurable.rbtest/models/setting_test.rbapp/models/lunchflow_item/importer.rbapp/models/setting.rbapp/controllers/settings/providers_controller.rbdb/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rbdb/schema.rbtest/controllers/settings/providers_controller_test.rb
**/*.{rb,js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
**/*.{rb,js,jsx,ts,tsx}: Make changes atomic, testable, and explain their impact briefly in code suggestions.
Respect existing tests and add tests when changing critical logic.
Files:
db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rbapp/models/provider/configurable.rbtest/models/setting_test.rbapp/models/lunchflow_item/importer.rbapp/models/setting.rbapp/controllers/settings/providers_controller.rbdb/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rbdb/schema.rbtest/controllers/settings/providers_controller_test.rb
db/migrate/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
Enforce simple validations in the database (NULL constraints, unique indexes, etc.)
Files:
db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rbdb/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rb
app/models/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-design.mdc)
Domain models should not call Provider::Registry directly; use a Provided concern within the model’s namespace to select providers and expose convenience methods
Use ActiveRecord validations for forms and complex domain constraints.
app/models/**/*.rb: Place business logic in POROs and model classes under app/models
Models should answer questions about themselves (e.g., prefer account.balance_series over service objects)
Implement complex validations and business logic with ActiveRecord validations
Model-level validations may mirror DB constraints but are not strictly required
Files:
app/models/provider/configurable.rbapp/models/lunchflow_item/importer.rbapp/models/setting.rb
app/models/provider/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-design.mdc)
Concrete provider classes must be under the Provider:: namespace, inherit from Provider, wrap calls with with_provider_response, and raise on invalid/unavailable data
Files:
app/models/provider/configurable.rb
app/**/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Place Rails application Ruby code (models, controllers, services, jobs, mailers, components) under app/
Files:
app/models/provider/configurable.rbapp/models/lunchflow_item/importer.rbapp/models/setting.rbapp/controllers/settings/providers_controller.rb
app/{helpers,models}/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
Format currencies, numbers, and dates on the server side (Ruby) before sending to the client
Files:
app/models/provider/configurable.rbapp/models/lunchflow_item/importer.rbapp/models/setting.rb
app/{models,controllers,views}/**/*.{rb,erb}
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
Avoid N+1 queries
Files:
app/models/provider/configurable.rbapp/models/lunchflow_item/importer.rbapp/models/setting.rbapp/controllers/settings/providers_controller.rb
test/**/*_test.rb
📄 CodeRabbit inference engine (AGENTS.md)
Name Minitest files with *_test.rb and mirror the app/ structure under test/
test/**/*_test.rb: ALWAYS use Minitest + fixtures + Mocha for tests; NEVER RSpec or FactoryBot.
Use Mocha for mocking in tests when necessary.
Use VCR for external API tests.
test/**/*_test.rb: Always use Minitest for tests; do not use RSpec
Do not use factories (e.g., FactoryBot) in tests; rely on fixtures instead
For tests needing many records, use Rails helpers to construct data and inline the creation in the test
Only write tests for critical and important code paths
Avoid tests that merely verify framework/ActiveRecord behavior
Test boundaries correctly: for queries, assert returned values; for commands, assert collaborators are called with correct params
Never test the implementation details of one class in another class’s test suite
Use the mocha gem for stubs and mocks
Prefer OpenStruct for mock instances; use a mock class for complex cases
Only mock what’s necessary; don’t mock return values unless they are under test
Files:
test/models/setting_test.rbtest/controllers/settings/providers_controller_test.rb
db/schema.rb
📄 CodeRabbit inference engine (.cursor/rules/project-design.mdc)
Treat db/schema.rb as the authoritative source of truth for model relationships
Files:
db/schema.rb
🧠 Learnings (14)
📓 Common learnings
Learnt from: CR
Repo: we-promise/sure PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-09-16T13:17:53.155Z
Learning: PRs should include clear description, linked issues, screenshots for UI changes, and migration notes; ensure CI, tests, RuboCop, and Biome are clean
📚 Learning: 2025-09-16T13:15:56.406Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/project-design.mdc:0-0
Timestamp: 2025-09-16T13:15:56.406Z
Learning: Applies to app/models/provider/concepts/**/*.rb : Define concept interfaces under app/models/provider/concepts (e.g., exchange_rate interface) to enable pluggable providers
Applied to files:
app/models/provider/configurable.rb
📚 Learning: 2025-09-16T13:15:56.406Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/project-design.mdc:0-0
Timestamp: 2025-09-16T13:15:56.406Z
Learning: Applies to app/models/provider/**/*.rb : Concrete provider classes must be under the Provider:: namespace, inherit from Provider, wrap calls with with_provider_response, and raise on invalid/unavailable data
Applied to files:
app/models/provider/configurable.rbtest/controllers/settings/providers_controller_test.rb
📚 Learning: 2025-09-16T13:15:56.406Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/project-design.mdc:0-0
Timestamp: 2025-09-16T13:15:56.406Z
Learning: Applies to app/models/**/provided.rb : Implement Provided concerns in each model namespace to (1) choose the concept provider and (2) expose convenience methods for accessing provider data
Applied to files:
app/models/provider/configurable.rb
📚 Learning: 2025-09-16T13:15:56.406Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/project-design.mdc:0-0
Timestamp: 2025-09-16T13:15:56.406Z
Learning: Applies to app/models/**/*.rb : Domain models should not call Provider::Registry directly; use a Provided concern within the model’s namespace to select providers and expose convenience methods
Applied to files:
app/models/provider/configurable.rb
📚 Learning: 2025-09-23T22:22:48.511Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/testing.mdc:0-0
Timestamp: 2025-09-23T22:22:48.511Z
Learning: Applies to test/**/*_test.rb : Avoid tests that merely verify framework/ActiveRecord behavior
Applied to files:
test/models/setting_test.rb
📚 Learning: 2025-09-23T22:22:48.511Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/testing.mdc:0-0
Timestamp: 2025-09-23T22:22:48.511Z
Learning: Applies to test/**/*_test.rb : For tests needing many records, use Rails helpers to construct data and inline the creation in the test
Applied to files:
test/models/setting_test.rb
📚 Learning: 2025-09-23T22:22:48.511Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/testing.mdc:0-0
Timestamp: 2025-09-23T22:22:48.511Z
Learning: Applies to test/**/*_test.rb : Do not use factories (e.g., FactoryBot) in tests; rely on fixtures instead
Applied to files:
test/models/setting_test.rb
📚 Learning: 2025-09-16T13:15:56.406Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/project-design.mdc:0-0
Timestamp: 2025-09-16T13:15:56.406Z
Learning: Applies to app/models/account.rb : Account syncs are orchestrated by Account#sync_data (auto-match transfers, compute balances from start_date..today, enrich transactions) and should run whenever an Entry is updated
Applied to files:
app/models/lunchflow_item/importer.rb
📚 Learning: 2025-09-13T11:36:45.479Z
Learnt from: alessiocappa
Repo: we-promise/sure PR: 141
File: app/models/enable_banking_account/processor.rb:72-79
Timestamp: 2025-09-13T11:36:45.479Z
Learning: The balance_calculator method pattern is consistent across banking integrations in the codebase. Both PlaidAccount::Processor and EnableBankingAccount::Processor use the same approach: `balance = account.current_balance || account.available_balance || 0` followed by `OpenStruct.new(balance: balance, cash_balance: balance)` without explicit requires, and include identical comments about not distinguishing cash vs non-cash balances for non-investment accounts.
Applied to files:
app/models/lunchflow_item/importer.rb
📚 Learning: 2025-09-13T11:27:55.271Z
Learnt from: alessiocappa
Repo: we-promise/sure PR: 141
File: app/controllers/enable_banking_items_controller.rb:48-62
Timestamp: 2025-09-13T11:27:55.271Z
Learning: The `create_enable_banking_item!` method in `Family::EnableBankingConnectable` uses `find_or_create_by(id: enable_banking_id)` to either find an existing EnableBankingItem or create a new one, so it automatically handles updates to existing items without creating duplicates.
Applied to files:
app/models/lunchflow_item/importer.rb
📚 Learning: 2025-09-16T13:15:56.406Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/project-design.mdc:0-0
Timestamp: 2025-09-16T13:15:56.406Z
Learning: Applies to db/schema.rb : Treat db/schema.rb as the authoritative source of truth for model relationships
Applied to files:
db/schema.rb
📚 Learning: 2025-09-23T22:21:06.637Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/project-conventions.mdc:0-0
Timestamp: 2025-09-23T22:21:06.637Z
Learning: Applies to db/migrate/**/*.rb : Enforce simple validations in the database (NULL constraints, unique indexes, etc.)
Applied to files:
db/schema.rb
📚 Learning: 2025-09-16T13:17:53.155Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-09-16T13:17:53.155Z
Learning: Applies to db/seeds.rb : Keep seed data definitions in db/seeds.rb
Applied to files:
db/schema.rb
🧬 Code graph analysis (5)
db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb (2)
app/models/provider/configurable.rb (1)
value(188-202)app/models/setting.rb (2)
key(53-63)key(65-83)
test/models/setting_test.rb (2)
app/models/provider/configurable.rb (1)
value(188-202)app/models/setting.rb (3)
delete(95-103)key?(86-92)dynamic_keys(106-108)
app/models/setting.rb (1)
app/models/provider/configurable.rb (1)
value(188-202)
app/controllers/settings/providers_controller.rb (1)
app/models/provider/configurable.rb (1)
value(188-202)
test/controllers/settings/providers_controller_test.rb (2)
test/test_helper.rb (1)
with_self_hosting(72-75)app/models/setting.rb (1)
key?(86-92)
🪛 GitHub Check: ci / lint
app/models/setting.rb
[failure] 112-112:
Layout/IndentationWidth: Use 2 (not 0) spaces for indented_internal_methods indentation.
🔇 Additional comments (14)
app/models/lunchflow_item/importer.rb (1)
32-37: LGTM! Critical bug fix to prevent importing all accounts.The change correctly filters to only accounts with an associated
account_provider, preventing the bug where all accounts (including orphaned ones) were being imported. This aligns with the migration that removes orphaned accounts and ensures only user-selected accounts are updated during sync.app/models/provider/configurable.rb (1)
4-5: LGTM! Documentation accurately reflects the new storage model.The updated comments clearly describe the new bracket-style access pattern and per-field storage approach, helping developers understand how settings are now stored individually rather than in a shared hash.
Also applies to: 189-190
db/schema.rb (1)
13-13: LGTM! Schema changes for recurring transaction enhancements.The new columns for tracking expected amounts (min, max, avg) and manual flag are well-defined with appropriate types and constraints. The nullable decimals allow flexibility for transactions without historical data.
Also applies to: 690-693
test/models/setting_test.rb (2)
10-13: LGTM! Proper test teardown for dynamic fields.The teardown ensures test isolation by cleaning up all dynamic field entries after each test, preventing cross-test pollution.
70-133: LGTM! Comprehensive test coverage for dynamic field storage.The new tests thoroughly cover the per-field storage functionality including setting, getting, deletion, existence checking, and interaction with declared fields. Well-structured and clear test cases.
app/controllers/settings/providers_controller.rb (1)
57-59: LGTM! Critical fix to prevent atomic update issues and collisions.The change from batched dynamic_fields updates to per-field writes (
Setting[key_str] = value) is a key improvement that prevents race conditions and accidental removals. Each field is now stored independently, eliminating the collision issues that occurred with the shared hash approach. The transaction boundary still ensures consistency.test/controllers/settings/providers_controller_test.rb (1)
44-55: LGTM! Tests thoroughly updated for per-field storage model.The tests comprehensively validate the new per-field storage behavior including:
- Individual field updates using bracket notation
- Preservation of unrelated fields during updates
- Proper nil value handling and entry deletion
- Sequential updates without conflicts
- Atomicity within transactions
All assertions and comments properly reflect the new storage semantics.
Also applies to: 59-80, 84-112, 114-140, 165-181, 184-219
db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb (2)
2-18: LGTM! Migration correctly converts hash to individual entries.The up migration properly:
- Returns early if no dynamic_fields record exists (line 5)
- Handles empty hash case gracefully
- Creates individual entries with
dynamic:prefix- Cleans up the old record
20-34: LGTM! Reversible migration with proper safeguards.The down migration correctly reverses the change by:
- Collecting all dynamic entries back into a hash
- Destroying the individual entries
- Only recreating the dynamic_fields record if there are entries (line 33)
This ensures the migration is fully reversible.
app/models/setting.rb (5)
14-15: Clear documentation of the new approach.The updated comments accurately explain the shift to individual dynamic entries and the benefits of this approach.
52-63: LGTM!The bracket-read implementation correctly prioritizes declared fields and safely falls back to individual dynamic entries using
find_bywith safe navigation.
86-92: LGTM!The
key?method correctly checks both declared fields and individual dynamic entries.
94-103: LGTM!The
deletemethod correctly prevents deletion of declared fields and returns the deleted value, following Ruby conventions.
106-108: LGTM!The
dynamic_keysmethod appropriately uses a LIKE query to enumerate all dynamic entries and strips the prefix.
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
app/models/setting.rb (1)
110-114: Fix indentation per RuboCop
dynamic_key_nameis still indented two spaces too deep inside theclass << selfblock, so lint continues to fail. Align it with the other class methods.Apply this diff to correct the indentation:
- private - - def dynamic_key_name(key_str) - "dynamic:#{key_str}" - end + private + + def dynamic_key_name(key_str) + "dynamic:#{key_str}" + end
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
app/models/setting.rb(3 hunks)app/views/lunchflow_items/select_accounts.html.erb(1 hunks)app/views/lunchflow_items/select_existing_account.html.erb(1 hunks)app/views/settings/providers/_provider_form.html.erb(1 hunks)
✅ Files skipped from review due to trivial changes (2)
- app/views/lunchflow_items/select_existing_account.html.erb
- app/views/settings/providers/_provider_form.html.erb
🧰 Additional context used
📓 Path-based instructions (15)
app/views/**/*.erb
📄 CodeRabbit inference engine (AGENTS.md)
app/views/**/*.erb: Keep heavy logic out of ERB views; prefer helpers/components instead
ERB templates are linted by erb-lint per .erb_lint.ymlAlways use the icon helper (icon) for icons; never call lucide_icon directly
Files:
app/views/lunchflow_items/select_accounts.html.erb
app/views/**/*.html.*
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
app/views/**/*.html.*: Use partials only for simple, context-specific, mostly static HTML content.
Prefer semantic HTML; use Turbo Frames where possible instead of client-side solutions.
Use query params for state, not localStorage or sessionStorage.
Always perform server-side formatting for currencies, numbers, and dates.
Files:
app/views/lunchflow_items/select_accounts.html.erb
**/*.{html,erb,slim,js,jsx,ts,tsx,css,scss}
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
Always use functional design tokens (e.g., text-primary, bg-container) from the design system; do not use raw colors or ad-hoc classes.
Files:
app/views/lunchflow_items/select_accounts.html.erb
app/views/**/*.html.erb
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
app/views/**/*.html.erb: Prefer native HTML elements (e.g., ,) over JS-based components
Leverage Turbo frames to break up pages instead of JS-driven client-side solutions
Prefer native client-side form validation when possible
Files:
app/views/lunchflow_items/select_accounts.html.erb
app/{models,controllers,views}/**/*.{rb,erb}
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
Avoid N+1 queries
Files:
app/views/lunchflow_items/select_accounts.html.erbapp/models/setting.rb
{app/javascript/controllers/**/*.{js,ts},app/views/**/*.erb,app/components/**/*.erb}
📄 CodeRabbit inference engine (.cursor/rules/stimulus_conventions.mdc)
Use declarative Stimulus actions in ERB (data-action) instead of imperative event listeners in controller lifecycle (e.g., avoid addEventListener in connect); controllers should just respond to actions
Files:
app/views/lunchflow_items/select_accounts.html.erb
{app/components/**/*.{js,ts,erb},app/views/**/*.erb}
📄 CodeRabbit inference engine (.cursor/rules/stimulus_conventions.mdc)
Component-scoped Stimulus controllers in app/components must be used only within their component views, not in app/views
Files:
app/views/lunchflow_items/select_accounts.html.erb
{app/views/**,app/helpers/**,app/javascript/controllers/**}
📄 CodeRabbit inference engine (.cursor/rules/ui-ux-design-guidelines.mdc)
{app/views/**,app/helpers/**,app/javascript/controllers/**}: Style UI using TailwindCSS v4.x with the custom design system defined in app/assets/tailwind/maybe-design-system.css
Always start by referencing app/assets/tailwind/maybe-design-system.css to understand available primitives, functional tokens, and component tokens before styling
Prefer functional tokens from the design system over raw Tailwind values (e.g., use text-primary, bg-container, border border-primary instead of text-white, bg-white, border-gray-200)
Files:
app/views/lunchflow_items/select_accounts.html.erb
{app/views/**,app/helpers/**}
📄 CodeRabbit inference engine (.cursor/rules/ui-ux-design-guidelines.mdc)
Always generate semantic HTML
Files:
app/views/lunchflow_items/select_accounts.html.erb
{app/views,app/components}/**/*.html.erb
📄 CodeRabbit inference engine (.cursor/rules/view_conventions.mdc)
{app/views,app/components}/**/*.html.erb: Keep domain logic out of ERB templates; compute values in component/controller code and reference them in the template
Integrate Stimulus declaratively in ERB: templates declare data-controller/data-action; controllers respond to those declarations
Pass data from Rails to Stimulus via data-*-value attributes, not inline JavaScript
Files:
app/views/lunchflow_items/select_accounts.html.erb
app/models/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-design.mdc)
Domain models should not call Provider::Registry directly; use a Provided concern within the model’s namespace to select providers and expose convenience methods
Use ActiveRecord validations for forms and complex domain constraints.
app/models/**/*.rb: Place business logic in POROs and model classes under app/models
Models should answer questions about themselves (e.g., prefer account.balance_series over service objects)
Implement complex validations and business logic with ActiveRecord validations
Model-level validations may mirror DB constraints but are not strictly required
Files:
app/models/setting.rb
app/**/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Place Rails application Ruby code (models, controllers, services, jobs, mailers, components) under app/
Files:
app/models/setting.rb
**/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Ruby style: 2-space indentation; snake_case for methods/variables; CamelCase for classes/modules
Files:
app/models/setting.rb
**/*.{rb,js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
**/*.{rb,js,jsx,ts,tsx}: Make changes atomic, testable, and explain their impact briefly in code suggestions.
Respect existing tests and add tests when changing critical logic.
Files:
app/models/setting.rb
app/{helpers,models}/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
Format currencies, numbers, and dates on the server side (Ruby) before sending to the client
Files:
app/models/setting.rb
🧠 Learnings (5)
📓 Common learnings
Learnt from: CR
Repo: we-promise/sure PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-09-16T13:17:53.155Z
Learning: PRs should include clear description, linked issues, screenshots for UI changes, and migration notes; ensure CI, tests, RuboCop, and Biome are clean
📚 Learning: 2025-09-23T22:23:22.963Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/view_conventions.mdc:0-0
Timestamp: 2025-09-23T22:23:22.963Z
Learning: Applies to app/{views,components}/**/*.html.erb : Keep domain logic out of ERB templates; compute classes and logic in component/Ruby code, not inline in the template
Applied to files:
app/views/lunchflow_items/select_accounts.html.erb
📚 Learning: 2025-09-13T11:36:45.479Z
Learnt from: alessiocappa
Repo: we-promise/sure PR: 141
File: app/models/enable_banking_account/processor.rb:72-79
Timestamp: 2025-09-13T11:36:45.479Z
Learning: The balance_calculator method pattern is consistent across banking integrations in the codebase. Both PlaidAccount::Processor and EnableBankingAccount::Processor use the same approach: `balance = account.current_balance || account.available_balance || 0` followed by `OpenStruct.new(balance: balance, cash_balance: balance)` without explicit requires, and include identical comments about not distinguishing cash vs non-cash balances for non-investment accounts.
Applied to files:
app/views/lunchflow_items/select_accounts.html.erb
📚 Learning: 2025-09-16T13:17:53.155Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-09-16T13:17:53.155Z
Learning: Applies to **/*.rb : Ruby style: 2-space indentation; snake_case for methods/variables; CamelCase for classes/modules
Applied to files:
app/models/setting.rb
📚 Learning: 2025-09-23T22:21:06.637Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/project-conventions.mdc:0-0
Timestamp: 2025-09-23T22:21:06.637Z
Learning: Applies to app/models/**/*.rb : Model-level validations may mirror DB constraints but are not strictly required
Applied to files:
app/models/setting.rb
🧬 Code graph analysis (1)
app/models/setting.rb (1)
app/models/provider/configurable.rb (1)
value(188-202)
🔇 Additional comments (1)
app/views/lunchflow_items/select_accounts.html.erb (1)
19-22: LGTM: Harmless formatting changes.The quote style adjustments have no functional impact and maintain consistency in the template.
Reuse the base class’ atomic setter to leverage its locking and cache invalidation.
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
app/models/setting.rb (1)
77-80: Upsert fixes the race condition from previous review.The atomic
upsertoperation at line 78 correctly addresses the prior race condition flagged in the previous review (wherefind_or_initialize_by+save!was non-atomic). Cache invalidation at line 79 is also correct.Optional refactor: Consider whether the base class
RailsSettings::Baseprovides an atomic setter you can delegate to (e.g., calling a base method with the dynamic key and value). This would centralize cache invalidation and leverage any existing locking/transaction logic.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
app/models/setting.rb(3 hunks)
🧰 Additional context used
📓 Path-based instructions (6)
app/models/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-design.mdc)
Domain models should not call Provider::Registry directly; use a Provided concern within the model’s namespace to select providers and expose convenience methods
Use ActiveRecord validations for forms and complex domain constraints.
app/models/**/*.rb: Place business logic in POROs and model classes under app/models
Models should answer questions about themselves (e.g., prefer account.balance_series over service objects)
Implement complex validations and business logic with ActiveRecord validations
Model-level validations may mirror DB constraints but are not strictly required
Files:
app/models/setting.rb
app/**/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Place Rails application Ruby code (models, controllers, services, jobs, mailers, components) under app/
Files:
app/models/setting.rb
**/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Ruby style: 2-space indentation; snake_case for methods/variables; CamelCase for classes/modules
Files:
app/models/setting.rb
**/*.{rb,js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
**/*.{rb,js,jsx,ts,tsx}: Make changes atomic, testable, and explain their impact briefly in code suggestions.
Respect existing tests and add tests when changing critical logic.
Files:
app/models/setting.rb
app/{helpers,models}/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
Format currencies, numbers, and dates on the server side (Ruby) before sending to the client
Files:
app/models/setting.rb
app/{models,controllers,views}/**/*.{rb,erb}
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
Avoid N+1 queries
Files:
app/models/setting.rb
🧠 Learnings (3)
📓 Common learnings
Learnt from: CR
Repo: we-promise/sure PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-09-16T13:17:53.155Z
Learning: PRs should include clear description, linked issues, screenshots for UI changes, and migration notes; ensure CI, tests, RuboCop, and Biome are clean
📚 Learning: 2025-09-16T13:17:53.155Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-09-16T13:17:53.155Z
Learning: Applies to **/*.rb : Ruby style: 2-space indentation; snake_case for methods/variables; CamelCase for classes/modules
Applied to files:
app/models/setting.rb
📚 Learning: 2025-09-23T22:21:06.637Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/project-conventions.mdc:0-0
Timestamp: 2025-09-23T22:21:06.637Z
Learning: Applies to app/models/**/*.rb : Model-level validations may mirror DB constraints but are not strictly required
Applied to files:
app/models/setting.rb
🧬 Code graph analysis (1)
app/models/setting.rb (1)
app/models/provider/configurable.rb (1)
value(188-202)
🔇 Additional comments (5)
app/models/setting.rb (5)
14-15: Good documentation of the storage model change.The comments clearly explain the shift from a shared hash to per-key entries and the motivation (preventing race conditions).
51-63: LGTM: Bracket reader correctly prioritizes declared fields.The fallback to
find_bywith dynamic key prefix is sound, and safe navigation handles missing entries gracefully.
84-91: LGTM: Key existence check is correct.The method correctly prioritizes declared fields and efficiently checks dynamic entry existence with
exists?.
104-107: LGTM: Dynamic keys enumeration is correct.The SQL LIKE query with parameterized placeholder safely retrieves all dynamic entries, and the prefix stripping produces clean key names.
109-113: LGTM: Private helper is well-scoped and correctly indented.The
dynamic_key_namehelper centralizes the "dynamic:" prefix logic, and the indentation now follows Ruby style (2 spaces).
Signed-off-by: soky srm <[email protected]>
…_entries.rb Signed-off-by: soky srm <[email protected]>
This reverts commit 1f2a21e.
…dividual_entries.rb" This reverts commit 29dcaaa.
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
app/models/setting.rb (2)
53-63: Consider leveraging the parent class's getter for caching.The current implementation uses
find_bydirectly (line 61), which queries the database on every access. The parent classRailsSettings::Baselikely has a caching layer for reads. For undeclared dynamic fields, you might benefit from calling the parent's[]accessor with thedynamic_keyto leverage that cache:def [](key) key_str = key.to_s if respond_to?(key_str) public_send(key_str) else # Delegate to parent's cached getter super(dynamic_key_name(key_str)) end endThis would align with the parent's caching strategy and potentially improve performance for frequently accessed dynamic settings.
72-81: Consider delegating to the parent class's setter for consistency.While
upsert(line 79) is atomic and resolves the race condition from earlier code, it bypasses the parent class's[]=logic, which may include callbacks, validations, or more sophisticated caching. Delegating to the base class ensures consistency and leverages its built-in mechanisms:else # Store as individual dynamic entry dynamic_key = dynamic_key_name(key_str) if value.nil? where(var: dynamic_key).destroy_all clear_cache else - # Use upsert for atomic insert/update to avoid race conditions - upsert({ var: dynamic_key, value: value.to_yaml }, unique_by: :var) - clear_cache + # Delegate to parent's atomic setter + super(dynamic_key, value) end endThis approach reuses the parent's atomic update logic and ensures that any parent-level side effects (logging, auditing, etc.) are preserved.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
app/models/setting.rb(3 hunks)
🧰 Additional context used
📓 Path-based instructions (6)
app/models/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-design.mdc)
Domain models should not call Provider::Registry directly; use a Provided concern within the model’s namespace to select providers and expose convenience methods
Use ActiveRecord validations for forms and complex domain constraints.
app/models/**/*.rb: Place business logic in POROs and model classes under app/models
Models should answer questions about themselves (e.g., prefer account.balance_series over service objects)
Implement complex validations and business logic with ActiveRecord validations
Model-level validations may mirror DB constraints but are not strictly required
Files:
app/models/setting.rb
app/**/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Place Rails application Ruby code (models, controllers, services, jobs, mailers, components) under app/
Files:
app/models/setting.rb
**/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Ruby style: 2-space indentation; snake_case for methods/variables; CamelCase for classes/modules
Files:
app/models/setting.rb
**/*.{rb,js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
**/*.{rb,js,jsx,ts,tsx}: Make changes atomic, testable, and explain their impact briefly in code suggestions.
Respect existing tests and add tests when changing critical logic.
Files:
app/models/setting.rb
app/{helpers,models}/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
Format currencies, numbers, and dates on the server side (Ruby) before sending to the client
Files:
app/models/setting.rb
app/{models,controllers,views}/**/*.{rb,erb}
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
Avoid N+1 queries
Files:
app/models/setting.rb
🧠 Learnings (3)
📓 Common learnings
Learnt from: CR
Repo: we-promise/sure PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-09-16T13:17:53.155Z
Learning: PRs should include clear description, linked issues, screenshots for UI changes, and migration notes; ensure CI, tests, RuboCop, and Biome are clean
📚 Learning: 2025-09-16T13:17:53.155Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-09-16T13:17:53.155Z
Learning: Applies to **/*.rb : Ruby style: 2-space indentation; snake_case for methods/variables; CamelCase for classes/modules
Applied to files:
app/models/setting.rb
📚 Learning: 2025-09-23T22:21:06.637Z
Learnt from: CR
Repo: we-promise/sure PR: 0
File: .cursor/rules/project-conventions.mdc:0-0
Timestamp: 2025-09-23T22:21:06.637Z
Learning: Applies to app/models/**/*.rb : Model-level validations may mirror DB constraints but are not strictly required
Applied to files:
app/models/setting.rb
🧬 Code graph analysis (1)
app/models/setting.rb (1)
app/models/provider/configurable.rb (1)
value(188-202)
🔇 Additional comments (2)
app/models/setting.rb (2)
94-104: LGTM—cache invalidation now present.The
deletemethod correctly invalidates the cache (line 102) after removing dynamic entries. This addresses the previous concern about stale cache entries after deletion.
111-115: LGTM—indentation corrected.The
dynamic_key_namehelper is properly indented per Ruby style guidelines. The previous indentation issue has been resolved.
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (3)
db/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rb (1)
23-27: Consider raisingActiveRecord::IrreversibleMigrationfor clarity.The
downmethod logs that restoration is impossible but doesn't raise an error, allowing rollback to silently succeed without actually restoring data. This could be confusing. Rails convention is to explicitly raiseActiveRecord::IrreversibleMigrationfor truly irreversible migrations.Apply this diff:
def down - # Cannot restore orphaned accounts that were deleted - # These were unused accounts from old behavior that shouldn't have been created - Rails.logger.info "Cannot restore orphaned LunchflowAccount records (data migration is irreversible)" + raise ActiveRecord::IrreversibleMigration, "Cannot restore orphaned LunchflowAccount records" endconfig/initializers/plaid.rb (1)
18-20: Consider adding optional logging for debugging.The rescue block appropriately handles database-not-ready scenarios. However, adding a debug-level log message could help troubleshoot initialization issues during development.
rescue ActiveRecord::NoDatabaseError, PG::ConnectionBad # Database doesn't exist yet, skip initialization + Rails.logger.debug("Skipping Plaid initialization: database not ready") if defined?(Rails.logger) nildb/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb (1)
2-18: Consider using upsert to handle interrupted migrations gracefully.The
create!call on line 10 will raise an error if adynamic:#{key}entry already exists. If the migration is interrupted after creating some entries but before destroying the olddynamic_fieldsrecord, re-running the migration would fail.Apply this diff to use
upsertfor safer re-execution:# Parse the hash and create individual entries dynamic_fields_hash = dynamic_fields_record.value || {} dynamic_fields_hash.each do |key, value| - Setting.create!( + Setting.upsert( + { var: "dynamic:#{key}", value: value }, + unique_by: :var + ) + end + + # Alternative: use find_or_create_by if upsert is not preferred + dynamic_fields_hash.each do |key, value| + Setting.find_or_create_by!(var: "dynamic:#{key}") do |setting| - var: "dynamic:#{key}", - value: value - ) + setting.value = value + end end
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
config/initializers/plaid.rb(1 hunks)db/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rb(1 hunks)db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb(1 hunks)
🧰 Additional context used
📓 Path-based instructions (5)
db/migrate/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Place database migrations under db/migrate/
Simple validations like null checks and unique constraints should be handled by database constraints in migration files.
Files:
db/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rbdb/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb
**/*.rb
📄 CodeRabbit inference engine (AGENTS.md)
Ruby style: 2-space indentation; snake_case for methods/variables; CamelCase for classes/modules
Files:
db/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rbdb/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rbconfig/initializers/plaid.rb
**/*.{rb,js,jsx,ts,tsx}
📄 CodeRabbit inference engine (.github/copilot-instructions.md)
**/*.{rb,js,jsx,ts,tsx}: Make changes atomic, testable, and explain their impact briefly in code suggestions.
Respect existing tests and add tests when changing critical logic.
Files:
db/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rbdb/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rbconfig/initializers/plaid.rb
db/migrate/**/*.rb
📄 CodeRabbit inference engine (.cursor/rules/project-conventions.mdc)
Enforce simple validations in the database (NULL constraints, unique indexes, etc.)
Files:
db/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rbdb/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb
config/**
📄 CodeRabbit inference engine (AGENTS.md)
Store application and environment configuration under config/
Files:
config/initializers/plaid.rb
🧠 Learnings (3)
📓 Common learnings
Learnt from: CR
Repo: we-promise/sure PR: 0
File: AGENTS.md:0-0
Timestamp: 2025-09-16T13:17:53.155Z
Learning: PRs should include clear description, linked issues, screenshots for UI changes, and migration notes; ensure CI, tests, RuboCop, and Biome are clean
📚 Learning: 2025-09-13T11:40:26.913Z
Learnt from: alessiocappa
Repo: we-promise/sure PR: 141
File: app/models/enable_banking_entry/processor.rb:10-12
Timestamp: 2025-09-13T11:40:26.913Z
Learning: The plaid_id field is used consistently across multiple banking integrations (Plaid, SimpleFin, and Enable Banking) as a common external identifier field. A comprehensive refactor to use a proper external_id field should be done across all integrations in a separate PR to maintain consistency and avoid scope creep.
Applied to files:
config/initializers/plaid.rb
📚 Learning: 2025-09-13T12:23:31.324Z
Learnt from: alessiocappa
Repo: we-promise/sure PR: 141
File: db/migrate/20250825224717_add_enable_banking_domain.rb:3-34
Timestamp: 2025-09-13T12:23:31.324Z
Learning: When suggesting database schema improvements for banking integrations, consider consistency across all similar integrations (Plaid, SimpleFin, Enable Banking) and propose comprehensive changes in a separate PR rather than making changes to individual integrations in isolation.
Applied to files:
config/initializers/plaid.rb
🧬 Code graph analysis (2)
db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb (2)
app/models/provider/configurable.rb (1)
value(188-202)app/models/setting.rb (2)
key(53-63)key(65-83)
config/initializers/plaid.rb (4)
app/models/provider/factory.rb (1)
ensure_adapters_loaded(45-57)app/models/provider/configurable.rb (1)
reload_configuration(85-88)app/models/provider/plaid_adapter.rb (1)
reload_configuration(55-68)app/models/provider/plaid_eu_adapter.rb (1)
reload_configuration(47-60)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: ci / test
🔇 Additional comments (3)
db/migrate/20251111084519_remove_orphaned_lunchflow_accounts.rb (2)
1-1: LGTM!Migration class declaration follows Rails 7.2 conventions correctly.
6-15: The original review comment is incorrect and should be disregarded.The migration correctly uses
destroy_all. TheLunchflowAccountmodel has a dependent association (has_one :account_provider, as: :provider, dependent: :destroy), which means deleting aLunchflowAccountmust trigger deletion of its associatedaccount_providerrecord. Usingdelete_allas suggested would skip these callbacks and leave orphanedaccount_providerrecords behind, creating a different data consistency problem. The current implementation is appropriate for this cleanup task.Likely an incorrect or invalid review comment.
config/initializers/plaid.rb (1)
9-10: Guard correctly prevents initialization when settings table is missing.The table existence check appropriately handles scenarios where migrations haven't run yet. The rescue block below (lines 18-20) catches exceptions that might be raised by the
connectionortable_exists?calls themselves when the database doesn't exist.
| def down | ||
| # Collect all dynamic: entries back into a hash | ||
| dynamic_fields_hash = {} | ||
| Setting.where("var LIKE ?", "dynamic:%").find_each do |record| | ||
| key = record.var.sub(/^dynamic:/, "") | ||
| dynamic_fields_hash[key] = record.value | ||
| record.destroy | ||
| end | ||
|
|
||
| # Recreate the dynamic_fields record with the hash | ||
| Setting.create!( | ||
| var: "dynamic_fields", | ||
| value: dynamic_fields_hash | ||
| ) if dynamic_fields_hash.any? | ||
| end |
There was a problem hiding this comment.
Reorder operations to prevent potential data loss during rollback.
The current implementation destroys individual dynamic:* entries (line 26) before creating the dynamic_fields record (line 30). If the create! call fails, the dynamic entries are already destroyed, resulting in data loss.
Apply this diff to create the record first, then destroy entries:
def down
# Collect all dynamic: entries back into a hash
dynamic_fields_hash = {}
Setting.where("var LIKE ?", "dynamic:%").find_each do |record|
key = record.var.sub(/^dynamic:/, "")
dynamic_fields_hash[key] = record.value
- record.destroy
end
- # Recreate the dynamic_fields record with the hash
- Setting.create!(
- var: "dynamic_fields",
- value: dynamic_fields_hash
- ) if dynamic_fields_hash.any?
+ # Recreate the dynamic_fields record first to preserve data
+ if dynamic_fields_hash.any?
+ Setting.create!(
+ var: "dynamic_fields",
+ value: dynamic_fields_hash
+ )
+
+ # Only destroy individual entries after successfully creating the aggregated record
+ Setting.where("var LIKE ?", "dynamic:%").destroy_all
+ end
end🤖 Prompt for AI Agents
In db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb
around lines 20 to 34, change the rollback sequence so you create the
consolidated dynamic_fields record before deleting the individual dynamic:* rows
to avoid data loss; specifically, build the dynamic_fields hash from existing
dynamic:* records, then call Setting.create! for var: "dynamic_fields" with that
hash, and only after a successful create (ideally inside a single transaction)
delete the individual dynamic:* records (or destroy them after create!),
ensuring you wrap the create + delete steps in a transaction and let exceptions
bubble to prevent partial destructive changes.
* Some improvements - Fix issue with lunch flow accounts that were imported - Remove the period comparison section from reports * Add cleanup migration * FIX for dynamic config * Fix linter * FIX settings setter Reuse the base class’ atomic setter to leverage its locking and cache invalidation. * Make upsert atomic * Remove migration file Signed-off-by: soky srm <[email protected]> * Delete db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb Signed-off-by: soky srm <[email protected]> * Fix cache reset * Revert "Remove migration file" This reverts commit 1f2a21e. * Revert "Delete db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb" This reverts commit 29dcaaa. * Fix Plaid initialiser --------- Signed-off-by: soky srm <[email protected]>
* Some improvements - Fix issue with lunch flow accounts that were imported - Remove the period comparison section from reports * Add cleanup migration * FIX for dynamic config * Fix linter * FIX settings setter Reuse the base class’ atomic setter to leverage its locking and cache invalidation. * Make upsert atomic * Remove migration file Signed-off-by: soky srm <[email protected]> * Delete db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb Signed-off-by: soky srm <[email protected]> * Fix cache reset * Revert "Remove migration file" This reverts commit 1f2a21e. * Revert "Delete db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb" This reverts commit 29dcaaa. * Fix Plaid initialiser --------- Signed-off-by: soky srm <[email protected]>
* Some improvements - Fix issue with lunch flow accounts that were imported - Remove the period comparison section from reports * Add cleanup migration * FIX for dynamic config * Fix linter * FIX settings setter Reuse the base class’ atomic setter to leverage its locking and cache invalidation. * Make upsert atomic * Remove migration file Signed-off-by: soky srm <[email protected]> * Delete db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb Signed-off-by: soky srm <[email protected]> * Fix cache reset * Revert "Remove migration file" This reverts commit 1f2a21e. * Revert "Delete db/migrate/20251111094448_migrate_dynamic_fields_to_individual_entries.rb" This reverts commit 29dcaaa. * Fix Plaid initialiser --------- Signed-off-by: soky srm <[email protected]>
2 participants
Summary by CodeRabbit
Removed Features
Database Updates
Refactor
Style
Tests